© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28031
    Prev
    Next
    INDEX
    Explanations

    dates, identifiers, or common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IEF
    -0.96
     Ibadan
    -0.90
    yship
    -0.87
    unea
    -0.86
     acl
    -0.86
    Ϯ
    -0.86
    RTLE
    -0.85
    jesz
    -0.85
    timacy
    -0.85
    ulah
    -0.84
    POSITIVE LOGITS
     workplaces
    0.96
     dovrebbe
    0.94
     previous
    0.86
     should
    0.82
     прош
    0.80
     conocen
    0.78
     поможет
    0.77
     твори
    0.76
    ancienne
    0.76
    実現
    0.75
    Activations Density 0.001%

    No Known Activations